{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:ZPPNWJBC6LBU2JE7LF2QEPYHET","short_pith_number":"pith:ZPPNWJBC","schema_version":"1.0","canonical_sha256":"cbdedb2422f2c34d249f5975023f0724fa93b3f0d26a9f96726a97fd456f49e2","source":{"kind":"arxiv","id":"2605.13032","version":2},"attestation_state":"computed","paper":{"title":"What Information Matters? Graph Out-of-Distribution Detection via Tri-Component Information Decomposition","license":"http://creativecommons.org/licenses/by/4.0/","headline":"TIDE decomposes graph information into feature-specific, structure-specific and joint components to retain only label-relevant joint signals for improved out-of-distribution node detection.","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Danny Wang, Ruihong Qiu, Zi Huang","submitted_at":"2026-05-13T05:36:33Z","abstract_excerpt":"Graph neural networks are widely used for node classification, but they remain vulnerable to out-of-distribution (OOD) shifts in node features and graph structure. Prior work established that methods trained with standard supervised learning (SL) objectives tend to capture spurious signals from either features and/or structure, leaving the model fragile under distributional changes. To address this, we propose TIDE, a novel and effective Tri-Component Information Decomposition framework that explicitly decomposes information into feature-specific, structure-specific and joint components. TIDE "},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":true,"formal_links_present":true},"canonical_record":{"source":{"id":"2605.13032","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-13T05:36:33Z","cross_cats_sorted":[],"title_canon_sha256":"884cfa273ddbca2b3722ab471c4a7852e80f52a8a04ac34f4d0093b6b50ad74e","abstract_canon_sha256":"22c3d41c0972e868d92754e2efb08855e5233e59672145b98e89ed6767afa0f6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T03:08:59.706418Z","signature_b64":"oDh86t0ht5G7gqV2fuuZyvSgD1U+rAAv+mk/gx06BrjW14fAf/QH2IU3SEZfJ85vXI0X57k8N3U/BdMM3/oUBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cbdedb2422f2c34d249f5975023f0724fa93b3f0d26a9f96726a97fd456f49e2","last_reissued_at":"2026-05-18T03:08:59.705804Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T03:08:59.705804Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"What Information Matters? Graph Out-of-Distribution Detection via Tri-Component Information Decomposition","license":"http://creativecommons.org/licenses/by/4.0/","headline":"TIDE decomposes graph information into feature-specific, structure-specific and joint components to retain only label-relevant joint signals for improved out-of-distribution node detection.","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Danny Wang, Ruihong Qiu, Zi Huang","submitted_at":"2026-05-13T05:36:33Z","abstract_excerpt":"Graph neural networks are widely used for node classification, but they remain vulnerable to out-of-distribution (OOD) shifts in node features and graph structure. Prior work established that methods trained with standard supervised learning (SL) objectives tend to capture spurious signals from either features and/or structure, leaving the model fragile under distributional changes. To address this, we propose TIDE, a novel and effective Tri-Component Information Decomposition framework that explicitly decomposes information into feature-specific, structure-specific and joint components. TIDE "},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"TIDE explicitly decomposes information into feature-specific, structure-specific and joint components, preserving only the label-relevant part of the joint information while filtering out spurious feature- and structure-specific information.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That the joint information component can be reliably separated into label-relevant versus spurious parts and that removing the spurious specific components will produce a measurable entropy gap and higher ID confidence without harming ID accuracy.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"TIDE decomposes graph information into feature-specific, structure-specific, and joint components to retain only label-relevant joint signals and improve OOD detection over standard supervised learning.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"TIDE decomposes graph information into feature-specific, structure-specific and joint components to retain only label-relevant joint signals for improved out-of-distribution node detection.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"8e7c9f5280723e3d6f52cbda363786486aba2ee10cbcd2aee818bbb5309f9d39"},"source":{"id":"2605.13032","kind":"arxiv","version":2},"verdict":{"id":"e21fc5ea-96cf-45fb-9db4-049bdf6edc16","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-15T05:37:48.342808Z","strongest_claim":"TIDE explicitly decomposes information into feature-specific, structure-specific and joint components, preserving only the label-relevant part of the joint information while filtering out spurious feature- and structure-specific information.","one_line_summary":"TIDE decomposes graph information into feature-specific, structure-specific, and joint components to retain only label-relevant joint signals and improve OOD detection over standard supervised learning.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That the joint information component can be reliably separated into label-relevant versus spurious parts and that removing the spurious specific components will produce a measurable entropy gap and higher ID confidence without harming ID accuracy.","pith_extraction_headline":"TIDE decomposes graph information into feature-specific, structure-specific and joint components to retain only label-relevant joint signals for improved out-of-distribution node detection."},"references":{"count":133,"sample":[{"doi":"","year":null,"title":"Your classifier is secretly an energy based model and you should treat it like one , booktitle =","work_id":"02851fc1-372f-4f7b-b257-bf4a51cb34b6","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"Srikant , title =","work_id":"69a90bef-a8a1-45db-bb42-08718f01383e","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"CVPR , year =","work_id":"62d26c3e-fe18-48f7-a13a-b33c009ae852","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"NeurIPS , year =","work_id":"88297c32-cee8-4ca9-a5eb-71b2c2b3160b","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"NeurIPS , year =","work_id":"b2dbd2af-dfa7-4f2f-8c46-c69bc1c25f68","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":133,"snapshot_sha256":"1278d4eb508c175fc77f279873cd29b383e4d2479182613ee45e92f2d6ba2e70","internal_anchors":0},"formal_canon":{"evidence_count":2,"snapshot_sha256":"3cd33cf55920df7773abb0808e8dabac86fcd6181f24c597bcdf4f3b1df90544"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2605.13032","created_at":"2026-05-18T03:08:59.705902+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.13032v2","created_at":"2026-05-18T03:08:59.705902+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.13032","created_at":"2026-05-18T03:08:59.705902+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZPPNWJBC6LBU","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZPPNWJBC6LBU2JE7","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZPPNWJBC","created_at":"2026-05-18T12:33:37.589309+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":2,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZPPNWJBC6LBU2JE7LF2QEPYHET","json":"https://pith.science/pith/ZPPNWJBC6LBU2JE7LF2QEPYHET.json","graph_json":"https://pith.science/api/pith-number/ZPPNWJBC6LBU2JE7LF2QEPYHET/graph.json","events_json":"https://pith.science/api/pith-number/ZPPNWJBC6LBU2JE7LF2QEPYHET/events.json","paper":"https://pith.science/paper/ZPPNWJBC"},"agent_actions":{"view_html":"https://pith.science/pith/ZPPNWJBC6LBU2JE7LF2QEPYHET","download_json":"https://pith.science/pith/ZPPNWJBC6LBU2JE7LF2QEPYHET.json","view_paper":"https://pith.science/paper/ZPPNWJBC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.13032&json=true","fetch_graph":"https://pith.science/api/pith-number/ZPPNWJBC6LBU2JE7LF2QEPYHET/graph.json","fetch_events":"https://pith.science/api/pith-number/ZPPNWJBC6LBU2JE7LF2QEPYHET/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZPPNWJBC6LBU2JE7LF2QEPYHET/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZPPNWJBC6LBU2JE7LF2QEPYHET/action/storage_attestation","attest_author":"https://pith.science/pith/ZPPNWJBC6LBU2JE7LF2QEPYHET/action/author_attestation","sign_citation":"https://pith.science/pith/ZPPNWJBC6LBU2JE7LF2QEPYHET/action/citation_signature","submit_replication":"https://pith.science/pith/ZPPNWJBC6LBU2JE7LF2QEPYHET/action/replication_record"}},"created_at":"2026-05-18T03:08:59.705902+00:00","updated_at":"2026-05-18T03:08:59.705902+00:00"}